netdev - Re: [PATCH bpf-next v5 4/8] bpf: Introduce cgroup iter

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <CA+khW7gws1+bWQ2zpodVfAP_rtXv=8K3SSMLx4e9Lh4eKgtnmA@mail.gmail.com>
Date:   Thu, 28 Jul 2022 10:26:32 -0700
From:   Hao Luo <haoluo@...gle.com>
To:     Yonghong Song <yhs@...com>
Cc:     Kumar Kartikeya Dwivedi <memxor@...il.com>,
        Yosry Ahmed <yosryahmed@...gle.com>,
        Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>,
        Andrii Nakryiko <andrii@...nel.org>,
        Martin KaFai Lau <kafai@...com>,
        Song Liu <songliubraving@...com>, Tejun Heo <tj@...nel.org>,
        Zefan Li <lizefan.x@...edance.com>,
        Johannes Weiner <hannes@...xchg.org>,
        Shuah Khan <shuah@...nel.org>,
        Michal Hocko <mhocko@...nel.org>,
        KP Singh <kpsingh@...nel.org>,
        Benjamin Tissoires <benjamin.tissoires@...hat.com>,
        John Fastabend <john.fastabend@...il.com>,
        Michal Koutný <mkoutny@...e.com>,
        Roman Gushchin <roman.gushchin@...ux.dev>,
        David Rientjes <rientjes@...gle.com>,
        Stanislav Fomichev <sdf@...gle.com>,
        Greg Thelen <gthelen@...gle.com>,
        Shakeel Butt <shakeelb@...gle.com>,
        linux-kernel@...r.kernel.org, netdev@...r.kernel.org,
        bpf@...r.kernel.org, cgroups@...r.kernel.org
Subject: Re: [PATCH bpf-next v5 4/8] bpf: Introduce cgroup iter

On Wed, Jul 27, 2022 at 11:56 PM Yonghong Song <yhs@...com> wrote:
>
>
>
> On 7/22/22 1:33 PM, Hao Luo wrote:
> > On Fri, Jul 22, 2022 at 11:36 AM Kumar Kartikeya Dwivedi
> > <memxor@...il.com> wrote:
> >>
> >> On Fri, 22 Jul 2022 at 19:52, Yosry Ahmed <yosryahmed@...gle.com> wrote:
<...>
> >>> +
> >>> +static int __cgroup_iter_seq_show(struct seq_file *seq,
> >>> +                                 struct cgroup_subsys_state *css, int in_stop);
> >>> +
> >>> +static void cgroup_iter_seq_stop(struct seq_file *seq, void *v)
> >>> +{
> >>> +       /* pass NULL to the prog for post-processing */
> >>> +       if (!v)
> >>> +               __cgroup_iter_seq_show(seq, NULL, true);
> >>> +       mutex_unlock(&cgroup_mutex);
> >>
> >> I'm just curious, but would it be a good optimization (maybe in a
> >> follow up) to move this mutex_unlock before the check on v? That
> >> allows you to store/buffer some info you want to print as a compressed
> >> struct in a map, then write the full text to the seq_file outside the
> >> cgroup_mutex lock in the post-processing invocation.
> >>
> >> It probably also allows you to walk the whole hierarchy, if one
> >> doesn't want to run into seq_file buffer limit (or it can decide what
> >> to print within the limit in the post processing invocation), or it
> >> can use some out of band way (ringbuf, hashmap, etc.) to send the data
> >> to userspace. But all of this can happen without holding cgroup_mutex
> >> lock.
> >
> > Thanks Kumar.
> >
> > It sounds like an idea, but the key thing is not about moving
> > cgroup_mutex unlock before the check IMHO. The user can achieve
> > compression using the current infra. Compression could actually be
> > done in the bpf program. user can define and output binary content and
> > implement a userspace library to parse/decompress when reading out the
> > data.
>
> Right mutex_unlock() can be moved to the beginning of the
> function since the cgroup is not used in
>    __cgroup_iter_seq_show(seq, NULL, true)

Ok. Will do.